---
title: "Agent Tooling Agent Plugins — page 5 of 6"
description: "Plugins that build, inspect, or extend AI agents themselves: MCP server builders, skill and plugin authoring kits, memory and context management, prompt engineering, agent evaluation and observability."
canonical: https://agentpluginsdirectory.com/categories/agent-tooling/page/5
last-updated: 2026-08-25
---

# Agent Tooling Agent Plugins — page 5 of 6

Plugins that build, inspect, or extend AI agents themselves: MCP server builders, skill and plugin authoring kits, memory and context management, prompt engineering, agent evaluation and observability.

| Name | Description | Repo |
| --- | --- | --- |
| [plugin-creator](https://agentpluginsdirectory.com/plugins/plugin-creator) | Create portable Agent Plugins packages and isolated Codex or Claude projections. | OkYongChoi/closed-network-agent-plugins |
| [plugin-suite](https://agentpluginsdirectory.com/plugins/plugin-suite) | Doctor and creator suite for Agent Plugins 1.0.0 targets: deterministic gates, predicted-delta plans, proven reversible transformations. | jnyross/plugin-suite |
| [plugkit](https://agentpluginsdirectory.com/plugins/plugkit) | Official agent-plugkit maintenance plugin | agent-plugkit/plugkit-marketplace |
| [power-platform-mcp-connector-development](https://agentpluginsdirectory.com/plugins/power-platform-mcp-connector-development) | Complete toolkit for developing Power Platform custom connectors with Model Context Protocol integration for Microsoft Copilot Studio | paulasilvatech/Fabric-Agentic-SDLC |
| [princi](https://agentpluginsdirectory.com/plugins/princi) | Your personal context engine. Bootstrap any AI task by instantly warming up with relevant emails, Drive docs, Slack threads, and meeting decisions — before writing a single line of code. | princi-ai/princi-plugin |
| [project-flood](https://agentpluginsdirectory.com/plugins/project-flood) | A governed Copilot squad that can create bounded research and worktree swarms. | Slight76/Project-Flood |
| [project-knowledge-capture](https://agentpluginsdirectory.com/plugins/project-knowledge-capture) | Project Knowledge Capture: meetings, experiments, decisions, TicketLink/WikiTicket work, and project-memory nouns into a durable OKF knowledge graph. Multi-host bindings and write isolation for shared second brains. | SpillwaveSolutions/project-knowledge-capture |
| [remoteskill](https://agentpluginsdirectory.com/plugins/remoteskill) | Serves your RemoteSkill library to this agent. Your Agent Skills live in one hosted place and every agent reads the same copy. | LeeorNahum/RemoteSkill-Plugin |
| [rgh-mms](https://agentpluginsdirectory.com/plugins/rgh-mms) | rgh-mms claude-code agent surface (planner/implementor/reviewer/approver/researcher agents and skills), built from canonical policy/roles/workflows sources. | xchewtoyx/rgh-market |
| [rolecasting](https://agentpluginsdirectory.com/plugins/rolecasting) | Rolecasting: portable model selection and delegation topology for agent work. | nisavid/agents |
| [ryu.teams](https://agentpluginsdirectory.com/plugins/ryu.teams) | Teams: named groups of agents you can address as one. Governance shell over the in-crate teams store (agent-id membership only); no documents, no external dependencies. Runs the out-of-process ryu-teams sidecar; Core proxies /api/teams/* to it. | amajorai/ryu-teams |
| [second-brain-core](https://agentpluginsdirectory.com/plugins/second-brain-core) | Shared foundation for Spillwave ContentPack plugins: OKF schemas, typed edges, deterministic write helpers, progressive-disclosure packing, and write isolation. | SpillwaveSolutions/second-brain-core |
| [secret-word](https://agentpluginsdirectory.com/plugins/secret-word) | Verification fixture exposing separate secret words through a skill and an MCP tool. | alainux/turnloop |
| [session-handoff](https://agentpluginsdirectory.com/plugins/session-handoff) | Preserve intent, evidence, and workspace state when moving long coding-agent work into a fresh session. | mhaviv/session-handoff-skill |
| [shared-mcp](https://agentpluginsdirectory.com/plugins/shared-mcp) | Cursor/Codex で共通利用する MCP サーバ定義（chrome-devtools / bigquery / huggingface） | ababa831/my-agent-plugins |
| [skill-architect](https://agentpluginsdirectory.com/plugins/skill-architect) | Design and improve reusable Agent Skills. | mark-groves/skills-nexus |
| [skill-tuner](https://agentpluginsdirectory.com/plugins/skill-tuner) | Tells you whether a change to an agent-consumed document actually worked: paired comparison with a confidence interval and a non-inferiority margin, content-hashed provenance with drift detection, and an adversarial defect probe. Reads Anthropic's skill-creator benchmark output and supplies the verdict it stops short of. | StartupBros-com/skill-tuner |
| [skillbase](https://agentpluginsdirectory.com/plugins/skillbase) | Use and sync Skillbase skills from Cursor via MCP OAuth. | sshadmand/skillbase-cursor |
| [skills-sh-growth-loop](https://agentpluginsdirectory.com/plugins/skills-sh-growth-loop) | Measure skills.sh discoverability, track verified organic users, and run ethical community growth experiments. | L4A-ai/skills-sh-growth-loop |
| [skizl](https://agentpluginsdirectory.com/plugins/skizl) | Full lifecycle manager and optimizer for agentic skills — author, densify into micro-kernels, pack, unpack, pin, sym, diff, snapshot, bump, archive, fork, publish, and git-guard. | alexsmedile/skizl |
| [spillwave-skills-marketplace](https://agentpluginsdirectory.com/plugins/spillwave-skills-marketplace) | Spillwave skills catalog: Docker, LocalStack, Zola, macOS, Python, AWS CDK, Codebase Wizard, Google Docs style, UI Guard, STE100. | SpillwaveSolutions/skills-marketplace |
| [swarmforge](https://agentpluginsdirectory.com/plugins/swarmforge) | SwarmForge as an Agent Plugin: tmux-based multi-agent orchestration for git worktrees (two-pack / four-pack / six-pack workflows), with operational scripts, handoff helpers, constitution and role prompt templates. | aintoniodev/autoskilling |
| [system-architecture-capture](https://agentpluginsdirectory.com/plugins/system-architecture-capture) | System Architecture Capture: reverse-engineer services, packages, IaC, CI/CD, IAM, and runtime topology into a durable OKF knowledge graph. Multi-host bindings and write isolation for shared second brains. | SpillwaveSolutions/system-architecture-capture |
| [token-calculator](https://agentpluginsdirectory.com/plugins/token-calculator) | Analyze token usage, estimate API costs, compare AI models, and assess file sizes for context window optimization. A toolkit for understanding and managing AI resource consumption. | novanoticia/token-calculator-suite |
| [trace](https://agentpluginsdirectory.com/plugins/trace) | Viewer for Iva's Trace: the turn journal as a live schema, a turn feed and a replay. | smixs/iva-plugins |
| [trellis](https://agentpluginsdirectory.com/plugins/trellis) | Build project Playbooks agents can use to reliably repeat work. | neutral/trellis |
| [universal-plugin](https://agentpluginsdirectory.com/plugins/universal-plugin) | Research and design toolkit for building universal AI coding agent plugins that work across Claude Code, Cursor, Codex, and GitHub Copilot CLI. | cyberuni/universal-plugin |
| [uru](https://agentpluginsdirectory.com/plugins/uru) | Build, organize, and publish durable work through Uru. | Ignition-Forward/uru-plugins |
| [usable](https://agentpluginsdirectory.com/plugins/usable) | Knowledge-first workflow for agents backed by Usable. Search team knowledge before implementing, retrieve complete sources, separate evidence from assumptions, and verify before claiming success. | flowcore-io/usable-agent-plugin |
| [vibesnake-agent](https://agentpluginsdirectory.com/plugins/vibesnake-agent) | Play deterministic Vibe Snake matches through a local .NET 10 MCP host and produce verified replays. | blisspixel/VibeSnake |
| [wom.hermes-closure-gate](https://agentpluginsdirectory.com/plugins/wom.hermes-closure-gate) | Portable companion package for the Hermes pre_verify closure gate. | wommy/agents-wom-plugins |
| [yard](https://agentpluginsdirectory.com/plugins/yard) | Local control plane. Search, hydrate, and attach marketplace skills, hooks, and MCP over stdio. | yannelli/yard |
| [zep-memory](https://agentpluginsdirectory.com/plugins/zep-memory--getzep) | Use Zep as long-term memory for knowledge work. Bundles a skill plus the Zep Memory MCP server. | getzep/zep-memory-plugin |
| [agentic-bundle-aas-ai-product-evaluation-ops](https://agentpluginsdirectory.com/plugins/agentic-bundle-aas-ai-product-evaluation-ops) | Portable skills-only "AAS AI Product & Evaluation Ops" plugin from Agentic Awesome Skills. | sickn33/agentic-awesome-skills |
| [plugin-manager](https://agentpluginsdirectory.com/plugins/plugin-manager) | 管插件：搜插件市场、看某插件会带来哪些能力、安装（可填凭据）、停用/启用、卸载，以及导入自制或网址来的插件包。用户说「装个能做 X 的插件」「我装了哪些插件」「把那个插件卸了」时加载。只管插件本身；技能归 skill-manager，智能体归 agent-manager。 | ZJU-REAL/HugAgentOS |
| [everruns-dev](https://agentpluginsdirectory.com/plugins/everruns-dev) | Interact with the Everruns(Dev) managed harnesses platform. Manage harnesses, agents, capabilities, sessions, and applications. | everruns/everruns |
| [agent-toolkit-complete](https://agentpluginsdirectory.com/plugins/agent-toolkit-complete) | Full stable skill catalog coverage for consumers who want everything ( | ulises-jeremias/agent-toolkit |
| [minimax-code-trajectory](https://agentpluginsdirectory.com/plugins/minimax-code-trajectory) | Inspect and visualize local MiniMax Code session ledgers as privacy-aware trajectories through a dependency-free MCP server. | hetaoBackend/MiniMax-Code-Plugins |
| [prism-callee](https://agentpluginsdirectory.com/plugins/prism-callee) | Run the Prism Story and Epic lifecycles as workflows of specialized Callee subagents. | baldaworks/prism |
| [quota-dashboard](https://agentpluginsdirectory.com/plugins/quota-dashboard) | Real-time Quota & Usage Monitor Web Dashboard for Antigravity (AGY). | iicmaster/antigravity-plugins |
| [mcp-server-patterns](https://agentpluginsdirectory.com/plugins/mcp-server-patterns--minimax-ai) | Reference patterns for designing, evaluating, integrating, and debugging MCP servers without changing the active MCP configuration. | MiniMax-AI/MiniMax-Code-Plugins |
| [suggest-awesome-github-copilot](https://agentpluginsdirectory.com/plugins/suggest-awesome-github-copilot) | Discover and install GitHub Copilot assets from the awesome-copilot repository. | PlagueHO/plagueho.copilot |
| [context-hygiene](https://agentpluginsdirectory.com/plugins/context-hygiene) | trigger: context bloat, stale observations, resolved content inlined, noisy exploration. avoid: context rot and lost-in-the-middle failures. | open-coder-ai/chock-catalog |
| [session-instructions-loader](https://agentpluginsdirectory.com/plugins/session-instructions-loader) | Codex-only SessionStart hook that injects ancestor AGENTS.md files and repo-configured instruction files. | Ben2pc/auriga-cli |
| [mnemosyne-memory](https://agentpluginsdirectory.com/plugins/mnemosyne-memory) | Use Mnemosyne MCP as a selective, project-aware memory and handoff layer across agent sessions. | heyNag/charms |
| [autoresearch](https://agentpluginsdirectory.com/plugins/autoresearch) | Autonomous improvement engine for Claude Code. Runs an unbounded modify-verify-keep/discard loop against any mechanical metric. Includes planning wizard, security audit, shipping workflow, autonomous debugger, and autonomous fixer. | RDCrystalLab/agentic-plugins |
| [agent-plugin-authoring](https://agentpluginsdirectory.com/plugins/agent-plugin-authoring) | Authoring, migration, and linting tools for packaging Agent Skills into Agent Plugins v1.0.0 spec packages. | ghchinoy/agent-skills |
| [claude-code-for-codex](https://agentpluginsdirectory.com/plugins/claude-code-for-codex) | Use Claude Code from Codex to review code or delegate tasks. | tiennguyentt/agent-plugins |
